Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    General discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tha
    -0.07
    衆
    -0.07
    肖
    -0.07
    tom
    -0.07
    -door
    -0.07
     Xm
    -0.06
     kültür
    -0.06
    NSMutableDictionary
    -0.06
    .IndexOf
    -0.06
     Expert
    -0.06
    POSITIVE LOGITS
     regular
    0.07
     penetrate
    0.06
    _drop
    0.06
    deadline
    0.06
    leave
    0.06
    	count
    0.06
     Overnight
    0.06
    channel
    0.06
     opposes
    0.06
     FINAL
    0.06
    Act Density 0.132%

    No Known Activations